update real data examples code and rerun project.

[ml_measurement_error_public.git] / simulations / plot_dv_example.R

diff --git a/simulations/plot_dv_example.R b/simulations/plot_dv_example.R
index 961bc879c3cbbfa111a71785af70fca606c82adb..45a5d51827cf2cda733c48ddbd63876bc305feaf 100644 (file)
--- a/simulations/plot_dv_example.R
+++ b/simulations/plot_dv_example.R
@@ -6,208 +6,76 @@ library(filelock)
 library(argparser)
 
 parser <- arg_parser("Simulate data and fit corrected models.")
 library(argparser)
 
 parser <- arg_parser("Simulate data and fit corrected models.")

-parser <- add_argument(parser, "--infile", default="", help="name of the file to read.")
+parser <- add_argument(parser, "--infile", default="example_4.feather", help="name of the file to read.")
+parser <- add_argument(parser, "--remember-file", default="remembr.RDS", help="name of the remember file.")

 parser <- add_argument(parser, "--name", default="", help="The name to safe the data to in the remember file.")
 args <- parse_args(parser)
 
 parser <- add_argument(parser, "--name", default="", help="The name to safe the data to in the remember file.")
 args <- parse_args(parser)
 

-build_plot_dataset <- function(df){
-    x.naive <- df[,.(N, m, Bxy, Bxy.est.naive, Bxy.ci.lower.naive, Bxy.ci.upper.naive)]
-    x.naive <- x.naive[,':='(true.in.ci = as.integer((Bxy >= Bxy.ci.lower.naive) & (Bxy <= Bxy.ci.upper.naive)),
-                             zero.in.ci = (0 >= Bxy.ci.lower.naive) & (0 <= Bxy.ci.upper.naive),
-                             bias = Bxy - Bxy.est.naive,
-                             Bxy.est.naive = Bxy.est.naive,
-                             sign.correct = as.integer(sign(Bxy) == sign(Bxy.est.naive)))]
-
-    x.naive.plot <- x.naive[,.(p.true.in.ci = mean(true.in.ci),
-                               mean.bias = mean(bias),
-                               mean.est = mean(Bxy.est.naive),
-                               var.est = var(Bxy.est.naive),
-                               N.sims = .N,
-                               p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                               variable='x',
-                               method='Naive'
-                               ),
-                            by=c('N','m')]
+## summarize.estimator <- function(df, suffix='naive', coefname='x'){
+
+##     part <- df[,c('N',
+##                   'm',
+##                   'Bxy',
+##                   paste0('B',coefname,'y.est.',suffix),
+##                   paste0('B',coefname,'y.ci.lower.',suffix),
+##                   paste0('B',coefname,'y.ci.upper.',suffix),
+##                   'y_explained_variance',
+##                   'Bzy'
+##                   ),
+##                with=FALSE]

     
     

-
-    g.naive <- df[,.(N, m, Bgy, Bgy.est.naive, Bgy.ci.lower.naive, Bgy.ci.upper.naive)]
-    g.naive <- g.naive[,':='(true.in.ci = as.integer((Bgy >= Bgy.ci.lower.naive) & (Bgy <= Bgy.ci.upper.naive)),
-                             zero.in.ci = (0 >= Bgy.ci.lower.naive) & (0 <= Bgy.ci.upper.naive),
-                             bias = Bgy - Bgy.est.naive,
-                             Bgy.est.naive = Bgy.est.naive,
-                             sign.correct = as.integer(sign(Bgy) == sign(Bgy.est.naive)))]
-
-    g.naive.plot <- g.naive[,.(p.true.in.ci = mean(true.in.ci),
-                               mean.bias = mean(bias),
-                               mean.est = mean(Bgy.est.naive),
-                               var.est = var(Bgy.est.naive),
-                               N.sims = .N,
-                               p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                               variable='g',
-                               method='Naive'
-                               ),
-                            by=c('N','m')]
+##     true.in.ci <- as.integer((part$Bxy >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (part$Bxy <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]]))
+##     zero.in.ci <- as.integer(0 >= part[[paste0('B',coefname,'y.ci.lower.',suffix)]]) & (0 <= part[[paste0('B',coefname,'y.ci.upper.',suffix)]])
+##     bias <- part$Bxy - part[[paste0('B',coefname,'y.est.',suffix)]]
+##     sign.correct <- as.integer(sign(part$Bxy) == sign(part[[paste0('B',coefname,'y.est.',suffix)]]))
+
+##     part <- part[,':='(true.in.ci = true.in.ci,
+##                        zero.in.ci = zero.in.ci,
+##                        bias=bias,
+##                        sign.correct =sign.correct)]
+
+##     part.plot <- part[, .(p.true.in.ci = mean(true.in.ci),
+##                           mean.bias = mean(bias),
+##                           mean.est = mean(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+##                           var.est = var(.SD[[paste0('B',coefname,'y.est.',suffix)]]),
+##                           est.upper.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.95),
+##                           est.lower.95 = quantile(.SD[[paste0('B',coefname,'y.est.',suffix)]],0.05),
+##                           N.sims = .N,
+##                           p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
+##                           variable=coefname,
+##                           method=suffix
+##                           ),
+##                       by=c("N","m",'Bzy','y_explained_variance')
+##                       ]

     
     

+##     return(part.plot)
+## }

 
 

-    x.feasible <- df[,.(N, m, Bxy, Bxy.est.feasible, Bxy.ci.lower.feasible, Bxy.ci.upper.feasible)]
-    x.feasible <- x.feasible[,':='(true.in.ci = as.integer((Bxy >= Bxy.ci.lower.feasible) & (Bxy <= Bxy.ci.upper.feasible)),
-                                   zero.in.ci = (0 >= Bxy.ci.lower.feasible) & (0 <= Bxy.ci.upper.feasible),
-                                   bias = Bxy - Bxy.est.feasible,
-                                   Bxy.est.feasible = Bxy.est.feasible,
-                                   sign.correct = as.integer(sign(Bxy) == sign(Bxy.est.feasible)))]
-
-    x.feasible.plot <- x.feasible[,.(p.true.in.ci = mean(true.in.ci),
-                                     mean.bias = mean(bias),
-                                     mean.est = mean(Bxy.est.feasible),
-                                     var.est = var(Bxy.est.feasible),
-                                     N.sims = .N,
-                                     p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                     variable='x',
-                                     method='Feasible'
-                                     ),
-                                  by=c('N','m')]
-    
+source("summarize_estimator.R")

 
 

-    g.feasible <- df[,.(N, m, Bgy, Bgy.est.feasible, Bgy.ci.lower.feasible, Bgy.ci.upper.feasible)]
-    g.feasible <- g.feasible[,':='(true.in.ci = as.integer((Bgy >= Bgy.ci.lower.feasible) & (Bgy <= Bgy.ci.upper.feasible)),
-                                   zero.in.ci = (0 >= Bgy.ci.lower.feasible) & (0 <= Bgy.ci.upper.feasible),
-                                   bias = Bgy - Bgy.est.feasible,
-                                   Bgy.est.feasible = Bgy.est.feasible,
-                                   sign.correct = as.integer(sign(Bgy) == sign(Bgy.est.feasible)))]
-
-    g.feasible.plot <- g.feasible[,.(p.true.in.ci = mean(true.in.ci),
-                                     mean.bias = mean(bias),
-                                     mean.est = mean(Bgy.est.feasible),
-                                     var.est = var(Bgy.est.feasible),
-                                     N.sims = .N,
-                                     p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                     variable='g',
-                                     method='Feasible'
-                                     ),
-                                  by=c('N','m')]
-    
+build_plot_dataset <- function(df){

 
 

+    x.true <- summarize.estimator(df, 'true','x')
+    z.true <- summarize.estimator(df, 'true','z')

 
 

-    x.amelia.full <- df[,.(N, m, Bxy, Bxy.est.true, Bxy.ci.lower.amelia.full, Bxy.ci.upper.amelia.full, Bxy.est.amelia.full)]
-
-    x.amelia.full <- x.amelia.full[,':='(true.in.ci = (Bxy.est.true >= Bxy.ci.lower.amelia.full) & (Bxy.est.true <= Bxy.ci.upper.amelia.full),
-                                         zero.in.ci = (0 >= Bxy.ci.lower.amelia.full) & (0 <= Bxy.ci.upper.amelia.full),
-                                         bias = Bxy.est.true - Bxy.est.amelia.full,
-                                         sign.correct = sign(Bxy.est.true) == sign(Bxy.est.amelia.full))]
-
-    x.amelia.full.plot <- x.amelia.full[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                           mean.bias = mean(bias),
-                                           p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                           mean.est = mean(Bxy.est.amelia.full),
-                                           var.est = var(Bxy.est.amelia.full),
-                                           N.sims = .N,
-                                           variable='x',
-                                           method='Multiple imputation'
-                                           ),
-                                        by=c('N','m')]
-
-
-    g.amelia.full <- df[,.(N, m, Bgy.est.true, Bgy.est.amelia.full, Bgy.ci.lower.amelia.full, Bgy.ci.upper.amelia.full)]
-    g.amelia.full <- g.amelia.full[,':='(true.in.ci = (Bgy.est.true >= Bgy.ci.lower.amelia.full) & (Bgy.est.true <= Bgy.ci.upper.amelia.full),
-                                         zero.in.ci = (0 >= Bgy.ci.lower.amelia.full) & (0 <= Bgy.ci.upper.amelia.full),
-                                         bias =  Bgy.est.amelia.full - Bgy.est.true,
-                                         sign.correct = sign(Bgy.est.true) == sign(Bgy.est.amelia.full))]
-
-    g.amelia.full.plot <- g.amelia.full[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                           mean.bias = mean(bias),
-                                           p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                           mean.est = mean(Bgy.est.amelia.full),
-                                           var.est = var(Bgy.est.amelia.full),
-                                           N.sims = .N,
-                                           variable='g',
-                                           method='Multiple imputation'
-                                           ),
-                                        by=c('N','m')]
-
-    x.mle <- df[,.(N,m, Bxy.est.true, Bxy.est.mle, Bxy.ci.lower.mle, Bxy.ci.upper.mle)]
-
-    x.mle <- x.mle[,':='(true.in.ci = (Bxy.est.true >= Bxy.ci.lower.mle) & (Bxy.est.true <= Bxy.ci.upper.mle),
-                                         zero.in.ci = (0 >= Bxy.ci.lower.mle) & (0 <= Bxy.ci.upper.mle),
-                                         bias =  Bxy.est.mle - Bxy.est.true,
-                                         sign.correct = sign(Bxy.est.true) == sign(Bxy.est.mle))]
-
-    x.mle.plot <- x.mle[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                   mean.bias = mean(bias),
-                                   p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                   mean.est = mean(Bxy.est.mle),
-                                   var.est = var(Bxy.est.mle),
-                                   N.sims = .N,
-                                   variable='x',
-                                   method='Maximum Likelihood'
-                                   ),
-                                by=c('N','m')]
-
-
-
-    g.mle <- df[,.(N,m, Bgy.est.true, Bgy.est.mle, Bgy.ci.lower.mle, Bgy.ci.upper.mle)]
-
-    g.mle <- g.mle[,':='(true.in.ci = (Bgy.est.true >= Bgy.ci.lower.mle) & (Bgy.est.true <= Bgy.ci.upper.mle),
-                                         zero.in.ci = (0 >= Bgy.ci.lower.mle) & (0 <= Bgy.ci.upper.mle),
-                                         bias =  Bgy.est.mle - Bgy.est.true,
-                                         sign.correct = sign(Bgy.est.true) == sign(Bgy.est.mle))]
-
-    g.mle.plot <- g.mle[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                   mean.bias = mean(bias),
-                                   p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                   mean.est = mean(Bgy.est.mle),
-                                   var.est = var(Bgy.est.mle),
-                                   N.sims = .N,
-                                   variable='g',
-                                   method='Maximum Likelihood'
-                                   ),
-                                by=c('N','m')]
-
-
-
-
-    x.pseudo <- df[,.(N,m, Bxy.est.true, Bxy.est.pseudo, Bxy.ci.lower.pseudo, Bxy.ci.upper.pseudo)]
-
-    x.pseudo <- x.pseudo[,':='(true.in.ci = (Bxy.est.true >= Bxy.ci.lower.pseudo) & (Bxy.est.true <= Bxy.ci.upper.pseudo),
-                                         zero.in.ci = (0 >= Bxy.ci.lower.pseudo) & (0 <= Bxy.ci.upper.pseudo),
-                                         bias =  Bxy.est.pseudo - Bxy.est.true,
-                                         sign.correct = sign(Bxy.est.true) == sign(Bxy.est.pseudo))]
-
-    x.pseudo.plot <- x.pseudo[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                   mean.bias = mean(bias),
-                                   p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                   mean.est = mean(Bxy.est.pseudo),
-                                   var.est = var(Bxy.est.pseudo),
-                                   N.sims = .N,
-                                   variable='x',
-                                   method='Pseudo Likelihood'
-                                   ),
-                                by=c('N','m')]
-
-
-
-    g.pseudo <- df[,.(N,m, Bgy.est.true, Bgy.est.pseudo, Bgy.ci.lower.pseudo, Bgy.ci.upper.pseudo)]
-
-    g.pseudo <- g.pseudo[,':='(true.in.ci = (Bgy.est.true >= Bgy.ci.lower.pseudo) & (Bgy.est.true <= Bgy.ci.upper.pseudo),
-                                         zero.in.ci = (0 >= Bgy.ci.lower.pseudo) & (0 <= Bgy.ci.upper.pseudo),
-                                         bias =  Bgy.est.pseudo - Bgy.est.true,
-                                         sign.correct = sign(Bgy.est.true) == sign(Bgy.est.pseudo))]
-
-    g.pseudo.plot <- g.pseudo[,.(p.true.in.ci = mean(as.integer(true.in.ci)),
-                                   mean.bias = mean(bias),
-                                   p.sign.correct = mean(as.integer(sign.correct & (! zero.in.ci))),
-                                   mean.est = mean(Bgy.est.pseudo),
-                                   var.est = var(Bgy.est.pseudo),
-                                   N.sims = .N,
-                                   variable='g',
-                                   method='Pseudo Likelihood'
-                                   ),
-                                by=c('N','m')]
+    x.naive <- summarize.estimator(df, 'naive','x')
+    z.naive <- summarize.estimator(df, 'naive','z')
+    
+    x.feasible <- summarize.estimator(df, 'feasible','x')
+    z.feasible <- summarize.estimator(df, 'feasible','z')
+    
+    x.amelia.full <- summarize.estimator(df, 'amelia.full','x')
+    z.amelia.full <- summarize.estimator(df, 'amelia.full','z')

 
 

+    x.mle <- summarize.estimator(df, 'mle','x')
+    z.mle <- summarize.estimator(df, 'mle','z')

 
 

+    x.zhang <- summarize.estimator(df, 'zhang','x')
+    z.zhang <- summarize.estimator(df, 'zhang','z')

     
     accuracy <- df[,mean(accuracy)]
 
     
     accuracy <- df[,mean(accuracy)]
 

-    plot.df <- rbindlist(list(x.naive.plot,g.naive.plot,x.amelia.full.plot,g.amelia.full.plot,x.mle.plot, g.mle.plot, x.pseudo.plot, g.pseudo.plot, x.feasible.plot, g.feasible.plot),use.names=T)
+    plot.df <- rbindlist(list(x.true, z.true, x.naive,z.naive,x.amelia.full,z.amelia.full,x.mle, z.mle, x.zhang, z.zhang, x.feasible, z.feasible),use.names=T)

 
     plot.df[,accuracy := accuracy]
 
 
     plot.df[,accuracy := accuracy]
 


@@ -216,18 +84,38 @@ build_plot_dataset <- function(df){
     return(plot.df)
 }
 
     return(plot.df)
 }
 

+change.remember.file(args$remember_file, clear=TRUE)
+sims.df <- read_feather(args$infile)
+sims.df[,Bzx:=NA]
+sims.df[,y_explained_variance:=NA]
+sims.df[,accuracy_imbalance_difference:=NA]
+plot.df <- build_plot_dataset(sims.df)

 
 

-df <- read_feather(args$infile)
-plot.df <- build_plot_dataset(df)

 remember(plot.df,args$name)
 
 remember(plot.df,args$name)
 

+set.remember.prefix(gsub("plot.df.","",args$name))
+
+remember(median(sims.df$cor.xz),'med.cor.xz')
+remember(median(sims.df$accuracy),'med.accuracy')
+remember(median(sims.df$error.cor.x),'med.error.cor.x')
+remember(median(sims.df$error.cor.z),'med.error.cor.z')
+remember(median(sims.df$lik.ratio),'med.lik.ratio')

 
 

-## df[gmm.ER_pval<0.05]

 
 
 
 
 
 

+## df[gmm.ER_pval<0.05]
+## plot.df.test <- plot.df[,':='(method=factor(method,levels=c("Naive","Multiple imputation", "Multiple imputation (Classifier features unobserved)","Regression Calibration","2SLS+gmm","Bespoke MLE", "Feasible"),ordered=T),
+##                                    N=factor(N),
+##                                    m=factor(m))]
+

 
 

+## plot.df.test <- plot.df.test[(variable=='z') & (m != 1000) & (m!=500) & !is.na(p.true.in.ci) & (method!="Multiple imputation (Classifier features unobserved)")]
+## p <- ggplot(plot.df.test, aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method))
+## p <- p + geom_hline(aes(yintercept=-0.05),linetype=2)

 
 

+## p <- p + geom_pointrange() + facet_grid(m~N,as.table=F) + scale_x_discrete(labels=label_wrap_gen(4))
+## print(p)

 ## ggplot(plot.df[variable=='x'], aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) + geom_pointrange() + facet_grid(-m~N) + scale_x_discrete(labels=label_wrap_gen(10))
 
 ## ggplot(plot.df,aes(y=N,x=m,color=p.sign.correct)) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c(option='D') + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size") 
 ## ggplot(plot.df[variable=='x'], aes(y=mean.est, ymax=mean.est + var.est/2, ymin=mean.est-var.est/2, x=method)) + geom_pointrange() + facet_grid(-m~N) + scale_x_discrete(labels=label_wrap_gen(10))
 
 ## ggplot(plot.df,aes(y=N,x=m,color=p.sign.correct)) + geom_point() + facet_grid(variable ~ method) + scale_color_viridis_c(option='D') + theme_minimal() + xlab("Number of gold standard labels") + ylab("Total sample size")